© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63593
    Prev
    Next
    INDEX
    Explanations

    in a broad sense or narrow meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿ĥåĬ¨
    -0.09
    ovich
    -0.09
    管çIJĨä¸Ńå¿ĥ
    -0.09
    åĪĩ
    -0.09
    Ñĩем
    -0.09
    è¶Ĭå¤ļ
    -0.08
    举æĸ¹
    -0.08
    çľ¼åīį
    -0.08
    æĺ¼
    -0.08
    大éĩıçļĦ
    -0.08
    POSITIVE LOGITS
    é¢ģ
    0.11
    æĦıä¹īä¸Ĭ
    0.09
    ä¸įå¼Ģ
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.08
     senses
    0.08
    åIJ«ä¹ī
    0.08
    ä¾ĥ
    0.08
     못
    0.08
     Hab
    0.08
    ossal
    0.08
    Activations Density 0.103%

    No Known Activations